{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OVMLBTIGV2TLBS6UJL66YT74PE","short_pith_number":"pith:OVMLBTIG","schema_version":"1.0","canonical_sha256":"7558b0cd06aea6b0cbd44afdec4ffc792b9e2538cd77b31d27b1860d08ee86a5","source":{"kind":"arxiv","id":"1804.00222","version":3},"attestation_state":"computed","paper":{"title":"Meta-Learning Update Rules for Unsupervised Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Brian Cheung, Jascha Sohl-Dickstein, Luke Metz, Niru Maheswaranathan","submitted_at":"2018-03-31T22:44:28Z","abstract_excerpt":"A major goal of unsupervised learning is to discover data representations that are useful for subsequent tasks, without access to supervised labels during training. Typically, this involves minimizing a surrogate objective, such as the negative log likelihood of a generative model, with the hope that representations useful for subsequent tasks will arise as a side effect. In this work, we propose instead to directly target later desired tasks by meta-learning an unsupervised learning rule which leads to representations useful for those tasks. Specifically, we target semi-supervised classificat"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1804.00222","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-31T22:44:28Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"c2333451cdd43feedfd80203167d8931b6ce4f32ff0f7fc5021b79c2679d452a","abstract_canon_sha256":"74efde70ec08c4e77591a3d58de2688fac4f6d5ed84ddf0651e08a66ba834e62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:44.161943Z","signature_b64":"6/D2ieOtmlN+AwmNGn3c67bQ4zRNDHxkSZXcQaZmYmLBaZU94HOVwLo38iig/dzpe4Oi/qEC98GQkdrLSUcnAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7558b0cd06aea6b0cbd44afdec4ffc792b9e2538cd77b31d27b1860d08ee86a5","last_reissued_at":"2026-05-17T23:52:44.161257Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:44.161257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Learning Update Rules for Unsupervised Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Brian Cheung, Jascha Sohl-Dickstein, Luke Metz, Niru Maheswaranathan","submitted_at":"2018-03-31T22:44:28Z","abstract_excerpt":"A major goal of unsupervised learning is to discover data representations that are useful for subsequent tasks, without access to supervised labels during training. Typically, this involves minimizing a surrogate objective, such as the negative log likelihood of a generative model, with the hope that representations useful for subsequent tasks will arise as a side effect. In this work, we propose instead to directly target later desired tasks by meta-learning an unsupervised learning rule which leads to representations useful for those tasks. Specifically, we target semi-supervised classificat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.00222","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1804.00222","created_at":"2026-05-17T23:52:44.161383+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.00222v3","created_at":"2026-05-17T23:52:44.161383+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.00222","created_at":"2026-05-17T23:52:44.161383+00:00"},{"alias_kind":"pith_short_12","alias_value":"OVMLBTIGV2TL","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OVMLBTIGV2TLBS6U","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OVMLBTIG","created_at":"2026-05-18T12:32:43.782077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2602.21204","citing_title":"Test-Time Training with KV Binding Is Secretly Linear Attention","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2407.04620","citing_title":"Learning to (Learn at Test Time): RNNs with Expressive Hidden States","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OVMLBTIGV2TLBS6UJL66YT74PE","json":"https://pith.science/pith/OVMLBTIGV2TLBS6UJL66YT74PE.json","graph_json":"https://pith.science/api/pith-number/OVMLBTIGV2TLBS6UJL66YT74PE/graph.json","events_json":"https://pith.science/api/pith-number/OVMLBTIGV2TLBS6UJL66YT74PE/events.json","paper":"https://pith.science/paper/OVMLBTIG"},"agent_actions":{"view_html":"https://pith.science/pith/OVMLBTIGV2TLBS6UJL66YT74PE","download_json":"https://pith.science/pith/OVMLBTIGV2TLBS6UJL66YT74PE.json","view_paper":"https://pith.science/paper/OVMLBTIG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.00222&json=true","fetch_graph":"https://pith.science/api/pith-number/OVMLBTIGV2TLBS6UJL66YT74PE/graph.json","fetch_events":"https://pith.science/api/pith-number/OVMLBTIGV2TLBS6UJL66YT74PE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OVMLBTIGV2TLBS6UJL66YT74PE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OVMLBTIGV2TLBS6UJL66YT74PE/action/storage_attestation","attest_author":"https://pith.science/pith/OVMLBTIGV2TLBS6UJL66YT74PE/action/author_attestation","sign_citation":"https://pith.science/pith/OVMLBTIGV2TLBS6UJL66YT74PE/action/citation_signature","submit_replication":"https://pith.science/pith/OVMLBTIGV2TLBS6UJL66YT74PE/action/replication_record"}},"created_at":"2026-05-17T23:52:44.161383+00:00","updated_at":"2026-05-17T23:52:44.161383+00:00"}